I have a task of finding confidence interval for difference of two samples means (its ARPU - avarage revenue per user). I need to find confidence interval for (Mean1 - Mean2). My guess is to use bootstrap in this task, but I'm not sure how to calculate standart deviation and confidence interval for difference.

What formulas should I use to get correct statistics? First sample size 2 800 000 and its mean 754. Second sample size 115 000 and its mean 711.

I can make bootstrap for 100 times for first sample and 1000 times for the second (I don't have memory for more) and using R.

  • $\begingroup$ With those sample sizes sampling uncertao ty must bediminutive! But, spme doubt is on ordet, hpw was sampling done? It is difficult to imagine so large samples can be iid, there must be some substructure. Can you tell us how sampling was done? $\endgroup$ – kjetil b halvorsen Apr 14 '17 at 0:58

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.